AdaQE-CG uses context-aware adaptive query expansion and inter-card knowledge transfer from a MetaGAI Pool to generate higher-quality model and data cards than prior methods, validated on the new expert-annotated MetaGAI-Bench.
One explanation Does Not Ft All: A Toolkit and Taxonomy of AI Explainability Techniques
5 Pith papers cite this work, alongside 267 external citations. Polarity classification is still indexing.
5
Pith papers citing it
267
external citations · external index
years
2026 5representative citing papers
Agentic AI needs less routine interaction but more action-process, uncertainty, and coordination explanations, plus user-controlled customization, to support trust and agency.
XGBoost plus SHAP and Jensen–Shannon KDE tests on UAVIDS-2025 explain Wormhole/Blackhole false predictions as density-support overlap between attack classes.
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
citing papers explorer
-
AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
AdaQE-CG uses context-aware adaptive query expansion and inter-card knowledge transfer from a MetaGAI Pool to generate higher-quality model and data cards than prior methods, validated on the new expert-annotated MetaGAI-Bench.
-
Less Interaction But More Explanation: A Communication Perspective on Agentic AI Interfaces
Agentic AI needs less routine interaction but more action-process, uncertainty, and coordination explanations, plus user-controlled customization, to support trust and agency.
-
XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
XGBoost plus SHAP and Jensen–Shannon KDE tests on UAVIDS-2025 explain Wormhole/Blackhole false predictions as density-support overlap between attack classes.
-
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
- SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data